BriefGPT.xyz
May, 2020
分支定界算法中的变量选择强化学习
Reinforcement Learning for Variable Selection in a Branch and Bound Algorithm
HTML
PDF
Marc Etheve, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum
TL;DR
文章提出了一种名为FMSTS的新型增强学习方法，采用一种全新的分支策略来优化整数线性规划问题，具有一致性和泛化能力，并在计算实验中验证了其有效性。
Abstract
mixed integer linear programs
are commonly solved by
branch and bound
algorithms. A key factor of the efficiency of the most successful commercial solvers is their fine-tuned heuristics. In this paper, we leverag
→